Patch-Level Nuclear Pleomorphism Scoring Using Convolutional Neural Networks

Autor:	Umit Ince, Engin Bozaba, Cavit Kerem Kayhan, Gulsah Ozsoy, Fatma Tokat, Gizem Solmaz, Sercan Cayir, Leonardo O. Iheme, Cisem Yazici, Samet Ayalti
Rok vydání:	2021
Předmět:	business.industry Computer science Deep learning Classifier (linguistics) Labeled data Pattern recognition Artificial intelligence business F1 score Residual Convolutional neural network Test data Teaching hospital
Zdroj:	Computer Analysis of Images and Patterns ISBN: 9783030891275 CAIP (1)
Popis:	In an effort to ease the job of pathologists while examining Hematoxylin and Eosin stained breast tissue, this study presents a deep learning-based classifier of nuclear pleomorphism according to the Nottingham grading scale. We show that high classification accuracy is attainable without pre-segmenting the cell nuclei. The data used in the experiments was acquired from our partner teaching hospital. It consists of image patches that were extracted from whole slide images. Using the labeled data, we compared the performance of three state-of-the-art convolutional neural networks and tested the trained model on the unseen testing data. Our experiments revealed that the densely connected architecture (DenseNet) outperforms the residual network (ResNet) and the dual path networks (DPN) in terms of accuracy and F1 score. Specifically, we reached an overall validation accuracy and F1 score of over 0.96 and 0.94 respectively.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::1d7fd6e91ad7c98411e68922650dcc27 https://doi.org/10.1007/978-3-030-89128-2_18 Zobrazit plný text záznamu